© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10393
    Prev
    Next
    INDEX
    Explanations

    words related to stories, movies, media, and people

    oai_token-act-pair · gemini-2.0-flash

    television shows

    np_max-act · gemini-2.0-flash

    the show/thing

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.84
    Diweddarwch
    -0.83
     AssemblyProduct
    -0.81
     ſche
    -0.80
    
    -0.77
     houſe
    -0.77
    ItemBackground
    -0.75
    ]")]
    -0.75
    omiast
    -0.74
     avoient
    -0.72
    POSITIVE LOGITS
    — 
    0.63
     long
    0.61
     many
    0.59
     fact
    0.59
     only
    0.58
     notoriously
    0.57
     constant
    0.57
    INCT
    0.56
     increasingly
    0.56
    ceria
    0.55
    Activations Density 1.306%

    No Known Activations